Theoreticallyhugo
commited on
Commit
•
3cfcb87
1
Parent(s):
1221abe
Training in progress, epoch 13, checkpoint
Browse files
checkpoint-1053/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 592318676
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a53d89182ba28fd8cc74258466782289fbcb12ef7da1120aa825ce0acf394828
|
3 |
size 592318676
|
checkpoint-1053/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1014645498
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9f13648611ef17472a83ba53df9c071613e5aee795ac405d1f1d0a1ee584e1a9
|
3 |
size 1014645498
|
checkpoint-1053/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2a8fed4ff2e0a1f5b060e9416aef90a5efb47a3301fd9fdfb8a444f0ad6d3aa3
|
3 |
size 14244
|
checkpoint-1053/trainer_state.json
CHANGED
@@ -11,521 +11,521 @@
|
|
11 |
{
|
12 |
"epoch": 1.0,
|
13 |
"eval_B": {
|
14 |
-
"f1-score": 0.
|
15 |
-
"precision": 0.
|
16 |
-
"recall": 0.
|
17 |
-
"support":
|
18 |
},
|
19 |
"eval_I": {
|
20 |
-
"f1-score": 0.
|
21 |
-
"precision": 0.
|
22 |
-
"recall": 0.
|
23 |
-
"support":
|
24 |
},
|
25 |
"eval_O": {
|
26 |
-
"f1-score": 0.
|
27 |
-
"precision": 0.
|
28 |
-
"recall": 0.
|
29 |
-
"support":
|
30 |
},
|
31 |
-
"eval_accuracy": 0.
|
32 |
-
"eval_loss": 0.
|
33 |
"eval_macro avg": {
|
34 |
-
"f1-score": 0.
|
35 |
-
"precision": 0.
|
36 |
-
"recall": 0.
|
37 |
-
"support":
|
38 |
-
},
|
39 |
-
"eval_runtime": 4.
|
40 |
-
"eval_samples_per_second": 17.
|
41 |
-
"eval_steps_per_second": 2.
|
42 |
"eval_weighted avg": {
|
43 |
-
"f1-score": 0.
|
44 |
-
"precision": 0.
|
45 |
-
"recall": 0.
|
46 |
-
"support":
|
47 |
},
|
48 |
"step": 81
|
49 |
},
|
50 |
{
|
51 |
"epoch": 2.0,
|
52 |
"eval_B": {
|
53 |
-
"f1-score": 0.
|
54 |
-
"precision": 0.
|
55 |
-
"recall": 0.
|
56 |
-
"support":
|
57 |
},
|
58 |
"eval_I": {
|
59 |
-
"f1-score": 0.
|
60 |
-
"precision": 0.
|
61 |
-
"recall": 0.
|
62 |
-
"support":
|
63 |
},
|
64 |
"eval_O": {
|
65 |
-
"f1-score": 0.
|
66 |
-
"precision": 0.
|
67 |
-
"recall": 0.
|
68 |
-
"support":
|
69 |
},
|
70 |
-
"eval_accuracy": 0.
|
71 |
-
"eval_loss": 0.
|
72 |
"eval_macro avg": {
|
73 |
-
"f1-score": 0.
|
74 |
-
"precision": 0.
|
75 |
-
"recall": 0.
|
76 |
-
"support":
|
77 |
-
},
|
78 |
-
"eval_runtime": 4.
|
79 |
-
"eval_samples_per_second": 17.
|
80 |
-
"eval_steps_per_second": 2.
|
81 |
"eval_weighted avg": {
|
82 |
-
"f1-score": 0.
|
83 |
-
"precision": 0.
|
84 |
-
"recall": 0.
|
85 |
-
"support":
|
86 |
},
|
87 |
"step": 162
|
88 |
},
|
89 |
{
|
90 |
"epoch": 3.0,
|
91 |
"eval_B": {
|
92 |
-
"f1-score": 0.
|
93 |
-
"precision": 0.
|
94 |
-
"recall": 0.
|
95 |
-
"support":
|
96 |
},
|
97 |
"eval_I": {
|
98 |
-
"f1-score": 0.
|
99 |
-
"precision": 0.
|
100 |
-
"recall": 0.
|
101 |
-
"support":
|
102 |
},
|
103 |
"eval_O": {
|
104 |
-
"f1-score": 0.
|
105 |
-
"precision": 0.
|
106 |
-
"recall": 0.
|
107 |
-
"support":
|
108 |
},
|
109 |
-
"eval_accuracy": 0.
|
110 |
-
"eval_loss": 0.
|
111 |
"eval_macro avg": {
|
112 |
-
"f1-score": 0.
|
113 |
-
"precision": 0.
|
114 |
-
"recall": 0.
|
115 |
-
"support":
|
116 |
-
},
|
117 |
-
"eval_runtime": 4.
|
118 |
-
"eval_samples_per_second": 17.
|
119 |
-
"eval_steps_per_second": 2.
|
120 |
"eval_weighted avg": {
|
121 |
-
"f1-score": 0.
|
122 |
-
"precision": 0.
|
123 |
-
"recall": 0.
|
124 |
-
"support":
|
125 |
},
|
126 |
"step": 243
|
127 |
},
|
128 |
{
|
129 |
"epoch": 4.0,
|
130 |
"eval_B": {
|
131 |
-
"f1-score": 0.
|
132 |
-
"precision": 0.
|
133 |
-
"recall": 0.
|
134 |
-
"support":
|
135 |
},
|
136 |
"eval_I": {
|
137 |
-
"f1-score": 0.
|
138 |
-
"precision": 0.
|
139 |
-
"recall": 0.
|
140 |
-
"support":
|
141 |
},
|
142 |
"eval_O": {
|
143 |
-
"f1-score": 0.
|
144 |
-
"precision": 0.
|
145 |
-
"recall": 0.
|
146 |
-
"support":
|
147 |
},
|
148 |
-
"eval_accuracy": 0.
|
149 |
-
"eval_loss": 0.
|
150 |
"eval_macro avg": {
|
151 |
-
"f1-score": 0.
|
152 |
-
"precision": 0.
|
153 |
-
"recall": 0.
|
154 |
-
"support":
|
155 |
-
},
|
156 |
-
"eval_runtime": 4.
|
157 |
-
"eval_samples_per_second": 17.
|
158 |
-
"eval_steps_per_second": 2.
|
159 |
"eval_weighted avg": {
|
160 |
-
"f1-score": 0.
|
161 |
-
"precision": 0.
|
162 |
-
"recall": 0.
|
163 |
-
"support":
|
164 |
},
|
165 |
"step": 324
|
166 |
},
|
167 |
{
|
168 |
"epoch": 5.0,
|
169 |
"eval_B": {
|
170 |
-
"f1-score": 0.
|
171 |
-
"precision": 0.
|
172 |
-
"recall": 0.
|
173 |
-
"support":
|
174 |
},
|
175 |
"eval_I": {
|
176 |
-
"f1-score": 0.
|
177 |
-
"precision": 0.
|
178 |
-
"recall": 0.
|
179 |
-
"support":
|
180 |
},
|
181 |
"eval_O": {
|
182 |
-
"f1-score": 0.
|
183 |
-
"precision": 0.
|
184 |
-
"recall": 0.
|
185 |
-
"support":
|
186 |
},
|
187 |
-
"eval_accuracy": 0.
|
188 |
-
"eval_loss": 0.
|
189 |
"eval_macro avg": {
|
190 |
-
"f1-score": 0.
|
191 |
-
"precision": 0.
|
192 |
-
"recall": 0.
|
193 |
-
"support":
|
194 |
-
},
|
195 |
-
"eval_runtime": 4.
|
196 |
-
"eval_samples_per_second":
|
197 |
-
"eval_steps_per_second": 2.
|
198 |
"eval_weighted avg": {
|
199 |
-
"f1-score": 0.
|
200 |
-
"precision": 0.
|
201 |
-
"recall": 0.
|
202 |
-
"support":
|
203 |
},
|
204 |
"step": 405
|
205 |
},
|
206 |
{
|
207 |
"epoch": 6.0,
|
208 |
"eval_B": {
|
209 |
-
"f1-score": 0.
|
210 |
-
"precision": 0.
|
211 |
-
"recall": 0.
|
212 |
-
"support":
|
213 |
},
|
214 |
"eval_I": {
|
215 |
-
"f1-score": 0.
|
216 |
-
"precision": 0.
|
217 |
-
"recall": 0.
|
218 |
-
"support":
|
219 |
},
|
220 |
"eval_O": {
|
221 |
-
"f1-score": 0.
|
222 |
-
"precision": 0.
|
223 |
-
"recall": 0.
|
224 |
-
"support":
|
225 |
},
|
226 |
-
"eval_accuracy": 0.
|
227 |
-
"eval_loss": 0.
|
228 |
"eval_macro avg": {
|
229 |
-
"f1-score": 0.
|
230 |
-
"precision": 0.
|
231 |
-
"recall": 0.
|
232 |
-
"support":
|
233 |
-
},
|
234 |
-
"eval_runtime": 4.
|
235 |
-
"eval_samples_per_second":
|
236 |
-
"eval_steps_per_second": 2.
|
237 |
"eval_weighted avg": {
|
238 |
-
"f1-score": 0.
|
239 |
-
"precision": 0.
|
240 |
-
"recall": 0.
|
241 |
-
"support":
|
242 |
},
|
243 |
"step": 486
|
244 |
},
|
245 |
{
|
246 |
"epoch": 6.17,
|
247 |
-
"grad_norm":
|
248 |
"learning_rate": 1.7530864197530865e-05,
|
249 |
-
"loss": 0.
|
250 |
"step": 500
|
251 |
},
|
252 |
{
|
253 |
"epoch": 7.0,
|
254 |
"eval_B": {
|
255 |
-
"f1-score": 0.
|
256 |
-
"precision": 0.
|
257 |
-
"recall": 0.
|
258 |
-
"support":
|
259 |
},
|
260 |
"eval_I": {
|
261 |
-
"f1-score": 0.
|
262 |
-
"precision": 0.
|
263 |
-
"recall": 0.
|
264 |
-
"support":
|
265 |
},
|
266 |
"eval_O": {
|
267 |
-
"f1-score": 0.
|
268 |
-
"precision": 0.
|
269 |
-
"recall": 0.
|
270 |
-
"support":
|
271 |
},
|
272 |
-
"eval_accuracy": 0.
|
273 |
-
"eval_loss": 0.
|
274 |
"eval_macro avg": {
|
275 |
-
"f1-score": 0.
|
276 |
-
"precision": 0.
|
277 |
-
"recall": 0.
|
278 |
-
"support":
|
279 |
-
},
|
280 |
-
"eval_runtime": 4.
|
281 |
-
"eval_samples_per_second":
|
282 |
-
"eval_steps_per_second": 2.
|
283 |
"eval_weighted avg": {
|
284 |
-
"f1-score": 0.
|
285 |
-
"precision": 0.
|
286 |
-
"recall": 0.
|
287 |
-
"support":
|
288 |
},
|
289 |
"step": 567
|
290 |
},
|
291 |
{
|
292 |
"epoch": 8.0,
|
293 |
"eval_B": {
|
294 |
-
"f1-score": 0.
|
295 |
-
"precision": 0.
|
296 |
-
"recall": 0.
|
297 |
-
"support":
|
298 |
},
|
299 |
"eval_I": {
|
300 |
-
"f1-score": 0.
|
301 |
-
"precision": 0.
|
302 |
-
"recall": 0.
|
303 |
-
"support":
|
304 |
},
|
305 |
"eval_O": {
|
306 |
-
"f1-score": 0.
|
307 |
-
"precision": 0.
|
308 |
-
"recall": 0.
|
309 |
-
"support":
|
310 |
},
|
311 |
-
"eval_accuracy": 0.
|
312 |
-
"eval_loss": 0.
|
313 |
"eval_macro avg": {
|
314 |
-
"f1-score": 0.
|
315 |
-
"precision": 0.
|
316 |
-
"recall": 0.
|
317 |
-
"support":
|
318 |
-
},
|
319 |
-
"eval_runtime": 4.
|
320 |
-
"eval_samples_per_second":
|
321 |
-
"eval_steps_per_second": 2.
|
322 |
"eval_weighted avg": {
|
323 |
-
"f1-score": 0.
|
324 |
-
"precision": 0.
|
325 |
-
"recall": 0.
|
326 |
-
"support":
|
327 |
},
|
328 |
"step": 648
|
329 |
},
|
330 |
{
|
331 |
"epoch": 9.0,
|
332 |
"eval_B": {
|
333 |
-
"f1-score": 0.
|
334 |
-
"precision": 0.
|
335 |
-
"recall": 0.
|
336 |
-
"support":
|
337 |
},
|
338 |
"eval_I": {
|
339 |
-
"f1-score": 0.
|
340 |
-
"precision": 0.
|
341 |
-
"recall": 0.
|
342 |
-
"support":
|
343 |
},
|
344 |
"eval_O": {
|
345 |
-
"f1-score": 0.
|
346 |
-
"precision": 0.
|
347 |
-
"recall": 0.
|
348 |
-
"support":
|
349 |
},
|
350 |
-
"eval_accuracy": 0.
|
351 |
-
"eval_loss": 0.
|
352 |
"eval_macro avg": {
|
353 |
-
"f1-score": 0.
|
354 |
-
"precision": 0.
|
355 |
-
"recall": 0.
|
356 |
-
"support":
|
357 |
-
},
|
358 |
-
"eval_runtime": 4.
|
359 |
-
"eval_samples_per_second": 17.
|
360 |
-
"eval_steps_per_second": 2.
|
361 |
"eval_weighted avg": {
|
362 |
-
"f1-score": 0.
|
363 |
-
"precision": 0.
|
364 |
-
"recall": 0.
|
365 |
-
"support":
|
366 |
},
|
367 |
"step": 729
|
368 |
},
|
369 |
{
|
370 |
"epoch": 10.0,
|
371 |
"eval_B": {
|
372 |
-
"f1-score": 0.
|
373 |
-
"precision": 0.
|
374 |
-
"recall": 0.
|
375 |
-
"support":
|
376 |
},
|
377 |
"eval_I": {
|
378 |
-
"f1-score": 0.
|
379 |
-
"precision": 0.
|
380 |
-
"recall": 0.
|
381 |
-
"support":
|
382 |
},
|
383 |
"eval_O": {
|
384 |
-
"f1-score": 0.
|
385 |
-
"precision": 0.
|
386 |
-
"recall": 0.
|
387 |
-
"support":
|
388 |
},
|
389 |
-
"eval_accuracy": 0.
|
390 |
-
"eval_loss": 0.
|
391 |
"eval_macro avg": {
|
392 |
-
"f1-score": 0.
|
393 |
-
"precision": 0.
|
394 |
-
"recall": 0.
|
395 |
-
"support":
|
396 |
-
},
|
397 |
-
"eval_runtime": 4.
|
398 |
-
"eval_samples_per_second": 17.
|
399 |
-
"eval_steps_per_second": 2.
|
400 |
"eval_weighted avg": {
|
401 |
-
"f1-score": 0.
|
402 |
-
"precision": 0.
|
403 |
-
"recall": 0.
|
404 |
-
"support":
|
405 |
},
|
406 |
"step": 810
|
407 |
},
|
408 |
{
|
409 |
"epoch": 11.0,
|
410 |
"eval_B": {
|
411 |
-
"f1-score": 0.
|
412 |
-
"precision": 0.
|
413 |
-
"recall": 0.
|
414 |
-
"support":
|
415 |
},
|
416 |
"eval_I": {
|
417 |
-
"f1-score": 0.
|
418 |
-
"precision": 0.
|
419 |
-
"recall": 0.
|
420 |
-
"support":
|
421 |
},
|
422 |
"eval_O": {
|
423 |
-
"f1-score": 0.
|
424 |
-
"precision": 0.
|
425 |
-
"recall": 0.
|
426 |
-
"support":
|
427 |
},
|
428 |
-
"eval_accuracy": 0.
|
429 |
-
"eval_loss": 0.
|
430 |
"eval_macro avg": {
|
431 |
-
"f1-score": 0.
|
432 |
-
"precision": 0.
|
433 |
-
"recall": 0.
|
434 |
-
"support":
|
435 |
-
},
|
436 |
-
"eval_runtime": 4.
|
437 |
-
"eval_samples_per_second": 17.
|
438 |
-
"eval_steps_per_second": 2.
|
439 |
"eval_weighted avg": {
|
440 |
-
"f1-score": 0.
|
441 |
-
"precision": 0.
|
442 |
-
"recall": 0.
|
443 |
-
"support":
|
444 |
},
|
445 |
"step": 891
|
446 |
},
|
447 |
{
|
448 |
"epoch": 12.0,
|
449 |
"eval_B": {
|
450 |
-
"f1-score": 0.
|
451 |
-
"precision": 0.
|
452 |
-
"recall": 0.
|
453 |
-
"support":
|
454 |
},
|
455 |
"eval_I": {
|
456 |
-
"f1-score": 0.
|
457 |
-
"precision": 0.
|
458 |
-
"recall": 0.
|
459 |
-
"support":
|
460 |
},
|
461 |
"eval_O": {
|
462 |
-
"f1-score": 0.
|
463 |
-
"precision": 0.
|
464 |
-
"recall": 0.
|
465 |
-
"support":
|
466 |
},
|
467 |
-
"eval_accuracy": 0.
|
468 |
-
"eval_loss": 0.
|
469 |
"eval_macro avg": {
|
470 |
-
"f1-score": 0.
|
471 |
-
"precision": 0.
|
472 |
-
"recall": 0.
|
473 |
-
"support":
|
474 |
-
},
|
475 |
-
"eval_runtime": 4.
|
476 |
-
"eval_samples_per_second": 17.
|
477 |
-
"eval_steps_per_second": 2.
|
478 |
"eval_weighted avg": {
|
479 |
-
"f1-score": 0.
|
480 |
-
"precision": 0.
|
481 |
-
"recall": 0.
|
482 |
-
"support":
|
483 |
},
|
484 |
"step": 972
|
485 |
},
|
486 |
{
|
487 |
"epoch": 12.35,
|
488 |
-
"grad_norm": 0.
|
489 |
"learning_rate": 1.506172839506173e-05,
|
490 |
-
"loss": 0.
|
491 |
"step": 1000
|
492 |
},
|
493 |
{
|
494 |
"epoch": 13.0,
|
495 |
"eval_B": {
|
496 |
-
"f1-score": 0.
|
497 |
-
"precision": 0.
|
498 |
-
"recall": 0.
|
499 |
-
"support":
|
500 |
},
|
501 |
"eval_I": {
|
502 |
-
"f1-score": 0.
|
503 |
-
"precision": 0.
|
504 |
-
"recall": 0.
|
505 |
-
"support":
|
506 |
},
|
507 |
"eval_O": {
|
508 |
-
"f1-score": 0.
|
509 |
-
"precision": 0.
|
510 |
-
"recall": 0.
|
511 |
-
"support":
|
512 |
},
|
513 |
-
"eval_accuracy": 0.
|
514 |
-
"eval_loss": 0.
|
515 |
"eval_macro avg": {
|
516 |
-
"f1-score": 0.
|
517 |
-
"precision": 0.
|
518 |
-
"recall": 0.
|
519 |
-
"support":
|
520 |
-
},
|
521 |
-
"eval_runtime": 4.
|
522 |
-
"eval_samples_per_second": 17.
|
523 |
-
"eval_steps_per_second": 2.
|
524 |
"eval_weighted avg": {
|
525 |
-
"f1-score": 0.
|
526 |
-
"precision": 0.
|
527 |
-
"recall": 0.
|
528 |
-
"support":
|
529 |
},
|
530 |
"step": 1053
|
531 |
}
|
@@ -535,7 +535,7 @@
|
|
535 |
"num_input_tokens_seen": 0,
|
536 |
"num_train_epochs": 50,
|
537 |
"save_steps": 500,
|
538 |
-
"total_flos":
|
539 |
"train_batch_size": 4,
|
540 |
"trial_name": null,
|
541 |
"trial_params": null
|
|
|
11 |
{
|
12 |
"epoch": 1.0,
|
13 |
"eval_B": {
|
14 |
+
"f1-score": 0.8331822302810515,
|
15 |
+
"precision": 0.7901977644024075,
|
16 |
+
"recall": 0.8811121764141898,
|
17 |
+
"support": 1043.0
|
18 |
},
|
19 |
"eval_I": {
|
20 |
+
"f1-score": 0.9471294753175105,
|
21 |
+
"precision": 0.9443616777446711,
|
22 |
+
"recall": 0.9499135446685879,
|
23 |
+
"support": 17350.0
|
24 |
},
|
25 |
"eval_O": {
|
26 |
+
"f1-score": 0.8992868897421833,
|
27 |
+
"precision": 0.9103731674811195,
|
28 |
+
"recall": 0.8884673748103187,
|
29 |
+
"support": 9226.0
|
30 |
},
|
31 |
+
"eval_accuracy": 0.9267895289474637,
|
32 |
+
"eval_loss": 0.20478281378746033,
|
33 |
"eval_macro avg": {
|
34 |
+
"f1-score": 0.8931995317802484,
|
35 |
+
"precision": 0.8816442032093993,
|
36 |
+
"recall": 0.9064976986310321,
|
37 |
+
"support": 27619.0
|
38 |
+
},
|
39 |
+
"eval_runtime": 4.6128,
|
40 |
+
"eval_samples_per_second": 17.343,
|
41 |
+
"eval_steps_per_second": 2.168,
|
42 |
"eval_weighted avg": {
|
43 |
+
"f1-score": 0.9268447919078652,
|
44 |
+
"precision": 0.9271861479533134,
|
45 |
+
"recall": 0.9267895289474637,
|
46 |
+
"support": 27619.0
|
47 |
},
|
48 |
"step": 81
|
49 |
},
|
50 |
{
|
51 |
"epoch": 2.0,
|
52 |
"eval_B": {
|
53 |
+
"f1-score": 0.8682547399124939,
|
54 |
+
"precision": 0.8806706114398422,
|
55 |
+
"recall": 0.8561840843720039,
|
56 |
+
"support": 1043.0
|
57 |
},
|
58 |
"eval_I": {
|
59 |
+
"f1-score": 0.9590983771942466,
|
60 |
+
"precision": 0.9592919333448654,
|
61 |
+
"recall": 0.9589048991354466,
|
62 |
+
"support": 17350.0
|
63 |
},
|
64 |
"eval_O": {
|
65 |
+
"f1-score": 0.9226525313717006,
|
66 |
+
"precision": 0.9208594256100194,
|
67 |
+
"recall": 0.9244526338608281,
|
68 |
+
"support": 9226.0
|
69 |
},
|
70 |
+
"eval_accuracy": 0.9435171439950758,
|
71 |
+
"eval_loss": 0.16574698686599731,
|
72 |
"eval_macro avg": {
|
73 |
+
"f1-score": 0.9166685494928136,
|
74 |
+
"precision": 0.9202739901315756,
|
75 |
+
"recall": 0.9131805391227594,
|
76 |
+
"support": 27619.0
|
77 |
+
},
|
78 |
+
"eval_runtime": 4.6238,
|
79 |
+
"eval_samples_per_second": 17.302,
|
80 |
+
"eval_steps_per_second": 2.163,
|
81 |
"eval_weighted avg": {
|
82 |
+
"f1-score": 0.9434932036816766,
|
83 |
+
"precision": 0.9434846863370583,
|
84 |
+
"recall": 0.9435171439950758,
|
85 |
+
"support": 27619.0
|
86 |
},
|
87 |
"step": 162
|
88 |
},
|
89 |
{
|
90 |
"epoch": 3.0,
|
91 |
"eval_B": {
|
92 |
+
"f1-score": 0.8791725434884815,
|
93 |
+
"precision": 0.8625461254612546,
|
94 |
+
"recall": 0.8964525407478428,
|
95 |
+
"support": 1043.0
|
96 |
},
|
97 |
"eval_I": {
|
98 |
+
"f1-score": 0.9588372159825352,
|
99 |
+
"precision": 0.9557349825345015,
|
100 |
+
"recall": 0.9619596541786744,
|
101 |
+
"support": 17350.0
|
102 |
},
|
103 |
"eval_O": {
|
104 |
+
"f1-score": 0.9204284621270084,
|
105 |
+
"precision": 0.9282407407407407,
|
106 |
+
"recall": 0.9127465857359636,
|
107 |
+
"support": 9226.0
|
108 |
},
|
109 |
+
"eval_accuracy": 0.9430464535283681,
|
110 |
+
"eval_loss": 0.15394224226474762,
|
111 |
"eval_macro avg": {
|
112 |
+
"f1-score": 0.9194794071993417,
|
113 |
+
"precision": 0.9155072829121655,
|
114 |
+
"recall": 0.9237195935541602,
|
115 |
+
"support": 27619.0
|
116 |
+
},
|
117 |
+
"eval_runtime": 4.6233,
|
118 |
+
"eval_samples_per_second": 17.303,
|
119 |
+
"eval_steps_per_second": 2.163,
|
120 |
"eval_weighted avg": {
|
121 |
+
"f1-score": 0.9429985029052194,
|
122 |
+
"precision": 0.9430314866542512,
|
123 |
+
"recall": 0.9430464535283681,
|
124 |
+
"support": 27619.0
|
125 |
},
|
126 |
"step": 243
|
127 |
},
|
128 |
{
|
129 |
"epoch": 4.0,
|
130 |
"eval_B": {
|
131 |
+
"f1-score": 0.8800746616892207,
|
132 |
+
"precision": 0.8572727272727273,
|
133 |
+
"recall": 0.9041227229146692,
|
134 |
+
"support": 1043.0
|
135 |
},
|
136 |
"eval_I": {
|
137 |
+
"f1-score": 0.9537844036697248,
|
138 |
+
"precision": 0.9488876212207644,
|
139 |
+
"recall": 0.9587319884726225,
|
140 |
+
"support": 17350.0
|
141 |
},
|
142 |
"eval_O": {
|
143 |
+
"f1-score": 0.9100192149327477,
|
144 |
+
"precision": 0.9220157970853265,
|
145 |
+
"recall": 0.8983308042488619,
|
146 |
+
"support": 9226.0
|
147 |
},
|
148 |
+
"eval_accuracy": 0.9364929939534379,
|
149 |
+
"eval_loss": 0.19801080226898193,
|
150 |
"eval_macro avg": {
|
151 |
+
"f1-score": 0.9146260934305644,
|
152 |
+
"precision": 0.9093920485262728,
|
153 |
+
"recall": 0.9203951718787179,
|
154 |
+
"support": 27619.0
|
155 |
+
},
|
156 |
+
"eval_runtime": 4.6132,
|
157 |
+
"eval_samples_per_second": 17.342,
|
158 |
+
"eval_steps_per_second": 2.168,
|
159 |
"eval_weighted avg": {
|
160 |
+
"f1-score": 0.9363812792925563,
|
161 |
+
"precision": 0.9364514800186444,
|
162 |
+
"recall": 0.9364929939534379,
|
163 |
+
"support": 27619.0
|
164 |
},
|
165 |
"step": 324
|
166 |
},
|
167 |
{
|
168 |
"epoch": 5.0,
|
169 |
"eval_B": {
|
170 |
+
"f1-score": 0.883877159309021,
|
171 |
+
"precision": 0.8847262247838616,
|
172 |
+
"recall": 0.8830297219558965,
|
173 |
+
"support": 1043.0
|
174 |
},
|
175 |
"eval_I": {
|
176 |
+
"f1-score": 0.9591500482927107,
|
177 |
+
"precision": 0.9456643513331839,
|
178 |
+
"recall": 0.9730259365994236,
|
179 |
+
"support": 17350.0
|
180 |
},
|
181 |
"eval_O": {
|
182 |
+
"f1-score": 0.9191176470588236,
|
183 |
+
"precision": 0.9454503781801513,
|
184 |
+
"recall": 0.8942120095382614,
|
185 |
+
"support": 9226.0
|
186 |
},
|
187 |
+
"eval_accuracy": 0.9432999022412107,
|
188 |
+
"eval_loss": 0.20074255764484406,
|
189 |
"eval_macro avg": {
|
190 |
+
"f1-score": 0.9207149515535183,
|
191 |
+
"precision": 0.9252803180990656,
|
192 |
+
"recall": 0.9167558893645271,
|
193 |
+
"support": 27619.0
|
194 |
+
},
|
195 |
+
"eval_runtime": 4.6092,
|
196 |
+
"eval_samples_per_second": 17.356,
|
197 |
+
"eval_steps_per_second": 2.17,
|
198 |
"eval_weighted avg": {
|
199 |
+
"f1-score": 0.9429348139614955,
|
200 |
+
"precision": 0.9432916158141273,
|
201 |
+
"recall": 0.9432999022412107,
|
202 |
+
"support": 27619.0
|
203 |
},
|
204 |
"step": 405
|
205 |
},
|
206 |
{
|
207 |
"epoch": 6.0,
|
208 |
"eval_B": {
|
209 |
+
"f1-score": 0.8897338403041826,
|
210 |
+
"precision": 0.882186616399623,
|
211 |
+
"recall": 0.8974113135186961,
|
212 |
+
"support": 1043.0
|
213 |
},
|
214 |
"eval_I": {
|
215 |
+
"f1-score": 0.9624160683661308,
|
216 |
+
"precision": 0.9707969272268809,
|
217 |
+
"recall": 0.954178674351585,
|
218 |
+
"support": 17350.0
|
219 |
},
|
220 |
"eval_O": {
|
221 |
+
"f1-score": 0.9297955261331482,
|
222 |
+
"precision": 0.9161493950552341,
|
223 |
+
"recall": 0.9438543247344461,
|
224 |
+
"support": 9226.0
|
225 |
},
|
226 |
+
"eval_accuracy": 0.9485861182519281,
|
227 |
+
"eval_loss": 0.16565027832984924,
|
228 |
"eval_macro avg": {
|
229 |
+
"f1-score": 0.9273151449344872,
|
230 |
+
"precision": 0.9230443128939126,
|
231 |
+
"recall": 0.9318147708682424,
|
232 |
+
"support": 27619.0
|
233 |
+
},
|
234 |
+
"eval_runtime": 4.6219,
|
235 |
+
"eval_samples_per_second": 17.309,
|
236 |
+
"eval_steps_per_second": 2.164,
|
237 |
"eval_weighted avg": {
|
238 |
+
"f1-score": 0.9487745648174827,
|
239 |
+
"precision": 0.9491959030765336,
|
240 |
+
"recall": 0.9485861182519281,
|
241 |
+
"support": 27619.0
|
242 |
},
|
243 |
"step": 486
|
244 |
},
|
245 |
{
|
246 |
"epoch": 6.17,
|
247 |
+
"grad_norm": 4.767655849456787,
|
248 |
"learning_rate": 1.7530864197530865e-05,
|
249 |
+
"loss": 0.1585,
|
250 |
"step": 500
|
251 |
},
|
252 |
{
|
253 |
"epoch": 7.0,
|
254 |
"eval_B": {
|
255 |
+
"f1-score": 0.8802588996763754,
|
256 |
+
"precision": 0.85,
|
257 |
+
"recall": 0.912751677852349,
|
258 |
+
"support": 1043.0
|
259 |
},
|
260 |
"eval_I": {
|
261 |
+
"f1-score": 0.958423523458803,
|
262 |
+
"precision": 0.9354661691269275,
|
263 |
+
"recall": 0.9825360230547551,
|
264 |
+
"support": 17350.0
|
265 |
},
|
266 |
"eval_O": {
|
267 |
+
"f1-score": 0.9139526911210146,
|
268 |
+
"precision": 0.9664088931851136,
|
269 |
+
"recall": 0.8668978972469109,
|
270 |
+
"support": 9226.0
|
271 |
},
|
272 |
+
"eval_accuracy": 0.9412723125384699,
|
273 |
+
"eval_loss": 0.2591131329536438,
|
274 |
"eval_macro avg": {
|
275 |
+
"f1-score": 0.9175450380853977,
|
276 |
+
"precision": 0.917291687437347,
|
277 |
+
"recall": 0.9207285327180049,
|
278 |
+
"support": 27619.0
|
279 |
+
},
|
280 |
+
"eval_runtime": 4.617,
|
281 |
+
"eval_samples_per_second": 17.327,
|
282 |
+
"eval_steps_per_second": 2.166,
|
283 |
"eval_weighted avg": {
|
284 |
+
"f1-score": 0.9406164485555297,
|
285 |
+
"precision": 0.9425749115781907,
|
286 |
+
"recall": 0.9412723125384699,
|
287 |
+
"support": 27619.0
|
288 |
},
|
289 |
"step": 567
|
290 |
},
|
291 |
{
|
292 |
"epoch": 8.0,
|
293 |
"eval_B": {
|
294 |
+
"f1-score": 0.8687910028116214,
|
295 |
+
"precision": 0.84967919340055,
|
296 |
+
"recall": 0.8887823585810163,
|
297 |
+
"support": 1043.0
|
298 |
},
|
299 |
"eval_I": {
|
300 |
+
"f1-score": 0.9595010203788336,
|
301 |
+
"precision": 0.956997878562009,
|
302 |
+
"recall": 0.9620172910662824,
|
303 |
+
"support": 17350.0
|
304 |
},
|
305 |
"eval_O": {
|
306 |
+
"f1-score": 0.9212035166275324,
|
307 |
+
"precision": 0.9282491471332673,
|
308 |
+
"recall": 0.9142640364188164,
|
309 |
+
"support": 9226.0
|
310 |
},
|
311 |
+
"eval_accuracy": 0.9432999022412107,
|
312 |
+
"eval_loss": 0.2693409323692322,
|
313 |
"eval_macro avg": {
|
314 |
+
"f1-score": 0.9164985132726624,
|
315 |
+
"precision": 0.9116420730319422,
|
316 |
+
"recall": 0.9216878953553717,
|
317 |
+
"support": 27619.0
|
318 |
+
},
|
319 |
+
"eval_runtime": 4.6153,
|
320 |
+
"eval_samples_per_second": 17.333,
|
321 |
+
"eval_steps_per_second": 2.167,
|
322 |
"eval_weighted avg": {
|
323 |
+
"f1-score": 0.9432823550422136,
|
324 |
+
"precision": 0.9433417293609165,
|
325 |
+
"recall": 0.9432999022412107,
|
326 |
+
"support": 27619.0
|
327 |
},
|
328 |
"step": 648
|
329 |
},
|
330 |
{
|
331 |
"epoch": 9.0,
|
332 |
"eval_B": {
|
333 |
+
"f1-score": 0.8645343367826904,
|
334 |
+
"precision": 0.8485687903970452,
|
335 |
+
"recall": 0.8811121764141898,
|
336 |
+
"support": 1043.0
|
337 |
},
|
338 |
"eval_I": {
|
339 |
+
"f1-score": 0.9567003348057282,
|
340 |
+
"precision": 0.934535260814599,
|
341 |
+
"recall": 0.9799423631123919,
|
342 |
+
"support": 17350.0
|
343 |
},
|
344 |
"eval_O": {
|
345 |
+
"f1-score": 0.9104673003585861,
|
346 |
+
"precision": 0.9586479683567062,
|
347 |
+
"recall": 0.8668978972469109,
|
348 |
+
"support": 9226.0
|
349 |
},
|
350 |
+
"eval_accuracy": 0.9384481697382236,
|
351 |
+
"eval_loss": 0.3087053894996643,
|
352 |
"eval_macro avg": {
|
353 |
+
"f1-score": 0.910567323982335,
|
354 |
+
"precision": 0.9139173398561168,
|
355 |
+
"recall": 0.9093174789244975,
|
356 |
+
"support": 27619.0
|
357 |
+
},
|
358 |
+
"eval_runtime": 4.6156,
|
359 |
+
"eval_samples_per_second": 17.333,
|
360 |
+
"eval_steps_per_second": 2.167,
|
361 |
"eval_weighted avg": {
|
362 |
+
"f1-score": 0.9377758584761231,
|
363 |
+
"precision": 0.9393435743356523,
|
364 |
+
"recall": 0.9384481697382236,
|
365 |
+
"support": 27619.0
|
366 |
},
|
367 |
"step": 729
|
368 |
},
|
369 |
{
|
370 |
"epoch": 10.0,
|
371 |
"eval_B": {
|
372 |
+
"f1-score": 0.8803126526624329,
|
373 |
+
"precision": 0.897410358565737,
|
374 |
+
"recall": 0.8638542665388304,
|
375 |
+
"support": 1043.0
|
376 |
},
|
377 |
"eval_I": {
|
378 |
+
"f1-score": 0.9590983771942466,
|
379 |
+
"precision": 0.9592919333448654,
|
380 |
+
"recall": 0.9589048991354466,
|
381 |
+
"support": 17350.0
|
382 |
},
|
383 |
"eval_O": {
|
384 |
+
"f1-score": 0.9220456265542221,
|
385 |
+
"precision": 0.9197584124245038,
|
386 |
+
"recall": 0.9243442445263386,
|
387 |
+
"support": 9226.0
|
388 |
},
|
389 |
+
"eval_accuracy": 0.9437705927079184,
|
390 |
+
"eval_loss": 0.2796257436275482,
|
391 |
"eval_macro avg": {
|
392 |
+
"f1-score": 0.9204855521369671,
|
393 |
+
"precision": 0.9254869014450354,
|
394 |
+
"recall": 0.9157011367335386,
|
395 |
+
"support": 27619.0
|
396 |
+
},
|
397 |
+
"eval_runtime": 4.641,
|
398 |
+
"eval_samples_per_second": 17.238,
|
399 |
+
"eval_steps_per_second": 2.155,
|
400 |
"eval_weighted avg": {
|
401 |
+
"f1-score": 0.9437458232244597,
|
402 |
+
"precision": 0.9437490553802075,
|
403 |
+
"recall": 0.9437705927079184,
|
404 |
+
"support": 27619.0
|
405 |
},
|
406 |
"step": 810
|
407 |
},
|
408 |
{
|
409 |
"epoch": 11.0,
|
410 |
"eval_B": {
|
411 |
+
"f1-score": 0.8830917874396135,
|
412 |
+
"precision": 0.8899707887049659,
|
413 |
+
"recall": 0.8763183125599233,
|
414 |
+
"support": 1043.0
|
415 |
},
|
416 |
"eval_I": {
|
417 |
+
"f1-score": 0.9574634882843123,
|
418 |
+
"precision": 0.9647182727751448,
|
419 |
+
"recall": 0.9503170028818444,
|
420 |
+
"support": 17350.0
|
421 |
},
|
422 |
"eval_O": {
|
423 |
+
"f1-score": 0.9200619426496501,
|
424 |
+
"precision": 0.9067466582465004,
|
425 |
+
"recall": 0.9337741166269239,
|
426 |
+
"support": 9226.0
|
427 |
},
|
428 |
+
"eval_accuracy": 0.9419964517180202,
|
429 |
+
"eval_loss": 0.3198166787624359,
|
430 |
"eval_macro avg": {
|
431 |
+
"f1-score": 0.9202057394578587,
|
432 |
+
"precision": 0.9204785732422037,
|
433 |
+
"recall": 0.9201364773562305,
|
434 |
+
"support": 27619.0
|
435 |
+
},
|
436 |
+
"eval_runtime": 4.6345,
|
437 |
+
"eval_samples_per_second": 17.262,
|
438 |
+
"eval_steps_per_second": 2.158,
|
439 |
"eval_weighted avg": {
|
440 |
+
"f1-score": 0.942161111514465,
|
441 |
+
"precision": 0.9425303680165918,
|
442 |
+
"recall": 0.9419964517180202,
|
443 |
+
"support": 27619.0
|
444 |
},
|
445 |
"step": 891
|
446 |
},
|
447 |
{
|
448 |
"epoch": 12.0,
|
449 |
"eval_B": {
|
450 |
+
"f1-score": 0.871306005719733,
|
451 |
+
"precision": 0.8663507109004739,
|
452 |
+
"recall": 0.8763183125599233,
|
453 |
+
"support": 1043.0
|
454 |
},
|
455 |
"eval_I": {
|
456 |
+
"f1-score": 0.9576855173984852,
|
457 |
+
"precision": 0.9464205312922107,
|
458 |
+
"recall": 0.9692219020172911,
|
459 |
+
"support": 17350.0
|
460 |
},
|
461 |
"eval_O": {
|
462 |
+
"f1-score": 0.9162135168127844,
|
463 |
+
"precision": 0.9386084583901774,
|
464 |
+
"recall": 0.8948623455451984,
|
465 |
+
"support": 9226.0
|
466 |
},
|
467 |
+
"eval_accuracy": 0.9408740359897172,
|
468 |
+
"eval_loss": 0.35264310240745544,
|
469 |
"eval_macro avg": {
|
470 |
+
"f1-score": 0.9150683466436677,
|
471 |
+
"precision": 0.917126566860954,
|
472 |
+
"recall": 0.9134675200408043,
|
473 |
+
"support": 27619.0
|
474 |
+
},
|
475 |
+
"eval_runtime": 4.6326,
|
476 |
+
"eval_samples_per_second": 17.269,
|
477 |
+
"eval_steps_per_second": 2.159,
|
478 |
"eval_weighted avg": {
|
479 |
+
"f1-score": 0.9405699625961891,
|
480 |
+
"precision": 0.9407871989028143,
|
481 |
+
"recall": 0.9408740359897172,
|
482 |
+
"support": 27619.0
|
483 |
},
|
484 |
"step": 972
|
485 |
},
|
486 |
{
|
487 |
"epoch": 12.35,
|
488 |
+
"grad_norm": 0.3602512776851654,
|
489 |
"learning_rate": 1.506172839506173e-05,
|
490 |
+
"loss": 0.021,
|
491 |
"step": 1000
|
492 |
},
|
493 |
{
|
494 |
"epoch": 13.0,
|
495 |
"eval_B": {
|
496 |
+
"f1-score": 0.877092300334768,
|
497 |
+
"precision": 0.875,
|
498 |
+
"recall": 0.8791946308724832,
|
499 |
+
"support": 1043.0
|
500 |
},
|
501 |
"eval_I": {
|
502 |
+
"f1-score": 0.9597242793665263,
|
503 |
+
"precision": 0.9486991778353419,
|
504 |
+
"recall": 0.9710086455331413,
|
505 |
+
"support": 17350.0
|
506 |
},
|
507 |
"eval_O": {
|
508 |
+
"f1-score": 0.9203392649259936,
|
509 |
+
"precision": 0.9419040054464994,
|
510 |
+
"recall": 0.8997398655972252,
|
511 |
+
"support": 9226.0
|
512 |
},
|
513 |
+
"eval_accuracy": 0.943734385748941,
|
514 |
+
"eval_loss": 0.3594338297843933,
|
515 |
"eval_macro avg": {
|
516 |
+
"f1-score": 0.9190519482090961,
|
517 |
+
"precision": 0.9218677277606138,
|
518 |
+
"recall": 0.9166477140009498,
|
519 |
+
"support": 27619.0
|
520 |
+
},
|
521 |
+
"eval_runtime": 4.6042,
|
522 |
+
"eval_samples_per_second": 17.376,
|
523 |
+
"eval_steps_per_second": 2.172,
|
524 |
"eval_weighted avg": {
|
525 |
+
"f1-score": 0.943447393984779,
|
526 |
+
"precision": 0.9436461164304495,
|
527 |
+
"recall": 0.943734385748941,
|
528 |
+
"support": 27619.0
|
529 |
},
|
530 |
"step": 1053
|
531 |
}
|
|
|
535 |
"num_input_tokens_seen": 0,
|
536 |
"num_train_epochs": 50,
|
537 |
"save_steps": 500,
|
538 |
+
"total_flos": 1869226485562800.0,
|
539 |
"train_batch_size": 4,
|
540 |
"trial_name": null,
|
541 |
"trial_params": null
|
checkpoint-1053/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4856
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:821ca433db9ddb761291ab61fc06d651ad248cd9d560cdb25f7f905e5aaff14e
|
3 |
size 4856
|